Prediction of Earthquake Magnitude with Improved Accuracy using FPA-LS-SVM Model in Comparison with LS-SVM Model

The proposed study uses the least square support vector machine flower pollination algorithm to predict earth- quakes of new magnitudes with increased accuracy. Comparing the FPA-LS-SVM model to the least squares support vector machine LS-SVM model for increased precision algorithms for flower pollination: least squares support vector machines In this research study, the least square support vector machine (LS- SVM) and FPA-LS-SVM algorithms are implemented. Using the G power software, the sample size is computed as 10 per group with a pretest power of 80%, a threshold of 0.05%, and a confidence interval of 95%. The G power value ranges from 0.59 to 0.9. algorithms for flower pollination: least squares support vector machines The FPA-LS-SVM technique yields a higher classification rate of 96.91% than the least square support vector machine (LS-SVM) algorithm, which only achieves 95.09%. A significant difference (p < 0.05) has been observed between the two groups, with a significance value of 0.003.These findings demonstrate that, in terms of accuracy, the flower pollination algorithm least square support vector machine FPA-LS-SVM algorithm performs better (96.91%) than the flower pollination algorithm least square support vector machine LV-SVM algorithm (95.09%).